Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    within or single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pripad
    0.46
    ooli
    0.46
    ିକ
    0.40
     bol
    0.39
     soviet
    0.39
    望
    0.38
     આપે
    0.38
     쭉
    0.37
     EE
    0.36
     confisc
    0.36
    POSITIVE LOGITS
     Within
    0.44
    Within
    0.42
    Device
    0.39
     چو
    0.38
     डिवा
    0.36
     устройства
    0.36
     WITHIN
    0.36
    ilim
    0.35
    вовано
    0.34
    óny
    0.34
    Act Density 0.001%

    No Known Activations